@agent_forge/forge-dsh
Forge quality gates for DeepSeek Harness (dsh): task gates, read-before-edit, bash hazard interception and quality scoring, driven by the forge CLI through DSH's typed interception points.
112 results
Forge quality gates for DeepSeek Harness (dsh): task gates, read-before-edit, bash hazard interception and quality scoring, driven by the forge CLI through DSH's typed interception points.
Let agents search, read, and cite your local Zotero library: find papers, browse notes and annotations, pull evidence by question, open the source document, generate citations.
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
Tencent Cloud Service CLS observability plugin for DeepSeek Harness — direct upload to Tencent Cloud CLS
Out-of-tree DSH bug-fix and compatibility plugin collection
Wang Hong-inspired Notability academic handwritten PPT skill for DeepSeek Harness
行为管理插件:系统提示词行为约束 / 失败收敛并行度 / 连续失败用户介入 / 写后检查与 .bak 回滚,基于 DSH 真实插件 API
Omni - an Agent Reliability Kernel for DeepSeek Harness. Decide. Prepare. Verify: DSH owns execution, Omni owns reliability.
A calm, one-to-one Svelte companion surface for DeepSeek Harness
Route-aware Codex environment simulation for DeepSeek Harness, improving tool-call reliability for GPT and other Codex-adapted models
Lean DSH-only spec-driven development skills
Diagnose WSL/Windows proxy, Node 24 fetch, dsh web process env, proxy TCP listen, DeepSeek/npm/ModelScope reachability.
把 DeepSeek Harness 对话里的主语人称「我/你/I/me」渲染成 DeepSeek 蓝鲸图标:字体层零 DOM 改动、复制保留原字、深色模式白肚子固定。
Quality-aware plugin discovery inside DeepSeek Harness: ask your agent in natural language, get ranked dsh-plugin recommendations with install commands, quality scores and risk flags. 质量感知的 DSH 插件发现:一句话问你的 agent,得到带质量分、风险提示与安装命令的插件推荐。
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
DSH-native uv environment manager with pip fallback and conda visibility
云 Well-Architected 六支柱评审框架:可靠性(用户经验目标/SLO/冗余/水平扩展/可观测性/优雅降级/恢复测试/无指责复盘)、成本优化、运维卓越、性能优化、安全、可持续性——设计原则+建议驱动架构评估与改进。受 google/skills(18.5k★ Apache-2.0)启发。
A DeepSeek Harness document parsing tool powered by LiteParse
DeepSeek Harness plugin: literature/related-work search plus one-shot Zotero import. Ships two skills (literature-search, zotero-import) and a zotero-import CLI so an agent can check an idea's novelty, then file the papers it finds straight into a running Zotero.
Screen-reader guidance and in-app accessibility diagnostics for DeepSeek Harness
dsh-codex-observability
Failure journal: every tool call that exits abnormally is written to a durable JSONL journal on disk, clustered by error signature, and readable back by the agent through a `failure_journal` tool.
Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.